AI Answers
from your Company Data
with Citations
Ask Context Link a question from any AI chat. Get one grounded paragraph with numbered citations back to your Notion, Docs, email, Basecamp, and more.
*Start for free
The answer,
not the chunks
Get context on [topic] returns raw snippets for the AI to reason over. Ask Context Link goes one step further: one grounded paragraph that directly answers your question, ready to paste, quote, or skim.
Every claim
cited to the source
Numbered citations back each fact to a specific Notion doc, Google Doc, email thread, or web page. Click a [1] and jump straight to the original. No black-box answers.
Ask your business
from the AI you already use
Give ChatGPT, Claude, and AI agents a way to ask your business questions or get the context they need. Context Link fetches the right source-backed context from your docs, website, inboxes, and files, so answers are grounded in your latest content.
works with:
*Don't see a pre-built connection? Download the custom-connections skill and Claude builds it for you. If Claude can read it, you can push it to Context Link.
features
Direct answers with receipts
Invoke /ask-question from Claude or ChatGPT. The same semantic search runs across your connected sources, then a small fast LLM composes one grounded paragraph with numbered citations. Every claim is traceable back to the source it came from.
features
Runs inside the AI you already use
Glean, Moveworks, Amazon Q, and Dropbox Dash lock you into their own chat interface. Ask Question is a Claude skill and ChatGPT connector, so you stay in the AI tool you already use and get cited answers in the same conversation.
features
Searches your whole stack, not one source at a time
Connect Google Docs and Drive, OneDrive, Notion, Basecamp, Monday.com, websites, file stacks (PDFs, Word, Markdown), email inboxes (Gmail, Outlook, Zoho, Fastmail, IMAP), and custom connections. Ask Question searches them all in a single query. If Claude can read it, you can push it to Context Link.
features
Grounded, it won't invent facts
The synthesis LLM is instructed to ground every claim in the retrieved snippets. If your sources don't cover the question, the answer says so rather than making something up. Numbered citations mean you can always verify, fast.
See Ask Question in Claude
Industries
Context Link works with your kind of business.
Whatever you run, it probably lives in a variety of places. Connect them once, and Give AI a single way to talk to all of it.
Connect the support inbox, brand book, catalogue and help centre once, and AI gets a single place to ask your whole e-commerce business. From ChatGPT or Claude, ask what customers keep contacting support about, what you currently say about pricing, or how a product is described, and get source-backed answers instead of pasted-in context. When you settle something, like a returns policy or a brand rule, save it as a Memory so every AI tool reads the latest version.
Connect the docs you already keep, like specs, changelogs, interviews and support threads, and stop rebuilding that context in every AI tool. From inside ChatGPT or Claude, ask about your positioning, a past decision, or what users actually said in interviews, and get source-backed answers without knowing which doc holds them. Then save the canonical stuff, like your ICP or pricing rationale, as Memories that stay current as they change.
Connect your back-catalogue of briefs, case studies, brand books and project archives, and give AI one place to ask the whole studio. Ask anything and get source-backed answers grounded in your real history, so strategy stops half-remembering and starts citing, and every pitch stands on work you've actually done. Save the things you keep re-explaining, like your process or your point of view, as Memories any AI can pull into the next deck.
Your business lives in a variety of places, like docs, sites, inboxes and files. Connect them once and Context Link becomes the single place ChatGPT, Claude and agents can ask across all of it, returning source-backed answers without you guessing where the answer lives or pasting in background. Your business stops being something you re-explain to every AI tool, and becomes something they can simply talk to.
Workflows
Ask from inside the AI tools you already use
Type /ask-question what's our refund policy for annual plans? in Claude or ChatGPT. Context Link runs semantic search across your connected sources (Notion, Google Docs, email threads, websites), then routes the results through a small fast LLM for synthesis.
Workflows
One paragraph, numbered citations
The answer comes back with [1], [2], [3] markers clicking straight through to the Notion doc, Google Doc, email thread, or web page it pulled from. No parsing chunks. No reconciling three docs mid-reply. One grounded paragraph, ready to act on.
Workflows
Review and control from the Context Link app
See every question your AI has asked, which sources it pulled from, and tune your connections and Modes to improve future answers. Sources sync every 24 hours, so tomorrow's answers reflect today's documents. Pro includes 2,000 LLM requests per month, shared across all LLM-powered features.
Share context across your team
Stop pasting the same docs into every chat. Share one link, and your team's AIs can pull the latest context from your connected sources—consistently, every time.
(ChatGPT)
(Claude)
agent 004
session
Frequently Asked Questions
What's the difference between Get Context and Ask Question?
Two skills, two outcomes. "Get context on [topic]" runs a semantic search across your connected sources and returns the raw matching snippets in markdown, ideal when the AI needs source material to reason over. "/ask-question [question]" (or "ask Context Link what...") runs the same retrieval under the hood, but a small fast LLM composes one grounded paragraph with numbered citations. Get Context is the primary workflow; Ask Question is a secondary sub-mode for when you want the direct answer, not the source material.
Can Ask Question make up facts that aren't in my sources?
The synthesis LLM is instructed to ground every claim in the retrieved snippets and cite them with [1], [2] markers. If your sources don't cover the question, the answer will say so rather than invent something. Every citation clicks through to the actual source doc, so you can always verify.
What sources can Ask Question search?
All of them, in a single query: Google Docs and Drive, OneDrive, Notion, Basecamp, Monday.com, any website (via sitemap or URL list), named file stacks (PDFs, Word, Markdown), email inboxes and folders (Gmail, Outlook, Zoho, Fastmail, and custom domains via IMAP), and custom connections. You don't have to guess which tool the answer lives in, Ask Question searches everything you've connected and synthesises one grounded paragraph. And if a tool isn't in the catalogue, the custom-connections skill lets your AI build the connection itself.
How is this different from Glean, Moveworks, or Amazon Q?
Those tools are capable, but they're their own chat interface, you have to switch apps to ask a question, then copy the answer back into ChatGPT or Claude if that's where your real work happens. Ask Question runs inside Claude and ChatGPT as a skill, so you stay in the AI tool you already use. Numbered citations click through to the real source (Notion, Google Docs, email thread) rather than a summarised excerpt inside a walled garden.
Is Ask Question available on the free plan?
Ask Question is a Pro feature. Pro includes 2,000 LLM requests per month, shared across all LLM-powered features. Starter accounts see an upgrade prompt when they hit Ask Question endpoints. Regular Get Context retrieval, the primary workflow, has no such gating and is available on all plans.